AI for Predicting Heart Transplant Outcomes
A recent review has highlighted the growing use of artificial intelligence (AI) in managing post-heart transplantation (HTx) and mechanical circulatory support (MCS) clinical care. This technology is particularly promising in the field of heart failure practice, where many decisions are often made based on expert opinions in the absence of high-quality data-driven evidence.
The review specifically focused on studies that examined post-HTx care, including post-operative management and long-term outcomes. The most common data sources used for development, training, and validation of AI algorithms are the United for Organ Sharing (UNOS) and the International Society of Heart and Lung Transplantation (ISHLT) registry. The primary outcomes studied include 1-year mortality or recipients, survival time, dependence on chronic dialysis, and graft survival. The machine learning models used include neural networks, support vector machines, random forests, and gradient-boosted machines. The predictive abilities of machine learning techniques may be limited by the quality of the clinical dataset.
The evidence revealed that AI can greatly improve the prediction of mortality outcomes in this patient population. However, there are still significant limitations to the use of AI in heart failure care. For example, there is a lack of external data validation and integration of multiple data modalities. The review found that there is a need for more mature AI algorithms for clinical application and external data validation to fully realize the potential benefits of AI in managing heart failure.
Al-Ani MA, Bai C, Hashky A, Parker AM, Vilaro JR, Aranda JM Jr, Shickel B, Rashidi P, Bihorac A, Ahmed MM, Mardini MT. Artificial intelligence guidance of advanced heart failure therapies: A systematic scoping review. Front Cardiovasc Med. 2023 Feb 24;10:1127716. doi: 10.3389/fcvm.2023.1127716. PMID: 36910520; PMCID: PMC9999024.
Post a Comment